| EUROPEAN UNION RELATIONS | |||||
| Bachelor | TR-NQF-HE: Level 6 | QF-EHEA: First Cycle | EQF-LLL: Level 6 | ||
| Course Code | Course Name | Semester | Theoretical | Practical | Credit | ECTS |
| CMP4501 | Introduction to Artificial Intelligence and Expert Systems | Spring | 3 | 0 | 3 | 6 |
| This catalog is for information purposes. Course status is determined by the relevant department at the beginning of semester. |
| Language of instruction: | English |
| Type of course: | Non-Departmental Elective |
| Course Level: | Bachelor’s Degree (First Cycle) |
| Mode of Delivery: | Face to face |
| Course Coordinator : | Dr. Öğr. Üyesi TEVFİK AYTEKİN |
| Recommended Optional Program Components: | None |
| Course Objectives: | The course introduces basics of artificial intelligence. Basic search techniques used for problem solving, fundamentals of knowledge representation and logical formalisms, basic learning algorithms, and fundamentals of expert systems will be introduced. |
|
The students who have succeeded in this course; I. Be able to formulate a state space description of a problem II. Be able to select and implement brute-force or heuristic algorithm for a problem. III. Be able to implement minimax search with alpha-beta pruning. IV. Be able to compare and evaluate the most common models for knowledge representation. V. Be able to explain the operation of the resolution technique for theorem proving. VI.Be able to explain the differences among supervised and unsupervised learning. VII. Be able to explain the concepts of overfitting, underfitting, bias, and variance. VIII. Be able to implement some of the basic algorithms for supervised learning and unsupervised learning. IX. Be able to describe fundamentals of expert systems and evaluate them. |
| Introduction to AI, state spaces and searching, heuristic functions and search, alpha-beta pruning, propositional and first-order predicate logic, propositional and first order inference, unification and resolution, linear regression, logistic regression, neural networks and backpropagation algorithm, Bayes’ rule and naive Bayes algorithm, clustering and k-means algorithm, fundementals of expert systems, software for expert systems. |
| Week | Subject | Related Preparation |
| 1) | Introduction to AI | |
| 2) | State spaces and searching. | |
| 3) | Heuristic functions and search | |
| 4) | Decisions in games, alpha-beta pruning. | |
| 5) | Propositional and first-order predicate logic | |
| 6) | Propositional and first order inference | |
| 7) | Unification and resolution | |
| 8) | Linear Regression | |
| 9) | Midterm | |
| 10) | Logistic Regression | |
| 11) | Neural networks and backpropagation algorithm. | |
| 12) | Bayes’s rule and naive Bayes algorithm. | |
| 13) | Clustering and k-means algorithm | |
| 14) | Fundementals of expert systems. | |
| 15) | Software for expert systems. |
| Course Notes / Textbooks: | Russell, S., Norvig, P., Artificial Intelligence: A Modern Approach, (3rd edition), 2009. Giarratano, J.C., Riley, G.D., Expert Systems: Principles and Programming, (4th edition), 2004. |
| References: | Yok - None |
| Semester Requirements | Number of Activities | Level of Contribution |
| Quizzes | 2 | % 10 |
| Project | 1 | % 20 |
| Midterms | 1 | % 30 |
| Final | 1 | % 40 |
| Total | % 100 | |
| PERCENTAGE OF SEMESTER WORK | % 40 | |
| PERCENTAGE OF FINAL WORK | % 60 | |
| Total | % 100 | |
| Activities | Number of Activities | Workload |
| Course Hours | 14 | 42 |
| Project | 4 | 20 |
| Homework Assignments | 10 | 20 |
| Quizzes | 2 | 8 |
| Midterms | 5 | 15 |
| Final | 5 | 20 |
| Total Workload | 125 | |
| No Effect | 1 Lowest | 2 Low | 3 Average | 4 High | 5 Highest |
| Program Outcomes | Level of Contribution | |
| 1) | To be able to examine, interpret data and assess ideas with the scientific methods in the area of EU studies. | 2 |
| 2) | To be able to inform authorities and institutions in the area of EU studies, to be able to transfer ideas and proposals supported by quantitative and qualitative data about the problems. | 2 |
| 3) | To be introduced to and to get involved in other disciplines that EU studies are strongly related with (political science, international relations, law, economics, sociology, etc.) and to be able to conduct multi-disciplinary research and analysis on European politics. | 3 |
| 4) | To be able to evaluate current news on European Union and Turkey-EU relations and identify, analyze current issues relating to the EU’s politics and policies. | 2 |
| 5) | To be able to use English in written and oral communication in general and in the field of EU studies in particular. | 1 |
| 6) | To have ethical, social and scientific values throughout the processes of collecting, interpreting, disseminating and implementing data related to EU studies. | 1 |
| 7) | To be able to assess the historical development, functioning of the institutions and decision-making system and common policies of the European Union throughout its economic and political integration in a supranational framework. | 2 |
| 8) | To be able to evaluate the current legal, financial and institutional changes that the EU is going through. | 2 |
| 9) | To explain the dynamics of enlargement processes of the EU by identifying the main actors and institutions involved and compare previous enlargement processes and accession process of Turkey. | 2 |
| 10) | To be able to analyze the influence of the EU on political, social and economic system of Turkey. | 2 |
| 11) | To acquire insight in EU project culture and to build up project preparation skills in line with EU format and develop the ability to work in groups and cooperate with peers. | 2 |
| 12) | To be able to recognize theories and concepts used by the discipline of international relations and relate them to the historical development of the EU as a unique post-War political project. | 3 |